Abstract

This study presents an image classification method for retrieval of images from a multi-varied MRI database. With the development of sophisticated medical imaging technology which helps doctors in diagnosis, medical image databases contain a huge amount of digital images. Magnetic Resonance Imaging (MRI) is a widely used imaging technique which picks signals from a body's magnetic particles spinning to magnetic tune and through a computer converts scanned data into pictures of internal organs. Image processing techniques are required to analyze medical images and retrieve it from database. The proposed framework extracts features using Moment Invariants (MI) and Wavelet Packet Tree (WPT). Extracted features are reduced using Correlation based Feature Selection (CFS) and a CFS with cuckoo search algorithm is proposed. Naïve Bayes and K-Nearest Neighbor (KNN) classify the selected features. National Biomedical Imaging Archive (NBIA) dataset including colon, brain and chest is used to evaluate the framework.

Keywords:

Correlation based Feature Selection (CFS), Magnetic Resonance Imaging (MRI), Na, National Biomedical Imaging Archive (NBIA) dataset,

References

1. Al-Kadi, O.S., 2008. Combined statistical and model based texture features for improved image classification. Proceeding of 4th IET International Conference on Advances in Medical, Signal and Information Processing (MEDSIP, 2008), pp: 1-4.
   CrossRef    
2. Chang, T. and C.C. Kuo, 1993. Texture analysis and classification with tree-structured wavelet transform. IEEE T. Image Process., 2(4): 429-441.
   CrossRef    PMid:18296228    
3. Chen, C.C., 1993. Improved moment invariants for shape discrimination. Pattern Recogn., 26(5): 683-686.
   CrossRef    
4. Florea, F.I., A. Rogozan, A. Bensrhair, J.N. Dacher and S. Darmoni, 2005. Modality categorization by textual annotations interpretation in medical imaging. Med. Inform. Bio-inform., pp: 1270-1274.
   
5. Hall, M.A., 1999. Correlation-based feature selection for machine learning. Ph.D. Thesis, the University of Waikato, Hamilton, New Zealand.
   
6. Kamencay, P., R. Hudec, M. Benco and M. Zachariasova, 2013. Feature extraction for object recognition using PCA-KNN with application to medical image analysis. Proceeding of 36th IEEE International Conference on Telecommunications and Signal Processing (TSP, 2013), pp: 830-834.
   CrossRef    
7. Karegowda, A.G. and M.A. Jayaram, 2009. Cascading GA and CFS for feature subset selection in medical data mining. Proceeding of IEEE International Advance Computing Conference (IACC, 2009), pp: 1428-1431.
   CrossRef    
8. Kassner, A. and R.E. Thornhill, 2010. Texture analysis: A review of neurologic MR imaging applications. Am. J. Neuroradiol., 31(5): 809-816.
   CrossRef    PMid:20395383    
9. Keivanfard, F., M. Teshnehlab, M.A. Shoorehdeli, K. Nie and M.Y. Su, 2010. Feature selection and classification of breast cancer on dynamic magnetic resonance imaging by using artificial neural networks. Proceeding of 17th Iranian Conference of Biomedical Engineering (ICBME, 2010), pp: 1-4.
   CrossRef    
10. Lederman, D., 2012. Texture-based continuous probabilistic framework for medical image representation and classification. Proceeding of 6th UKSim/AMSS European Symposium on Computer Modeling and Simulation (EMS), pp: 148-152.
    CrossRef    
11. Malik, A. and T. Zremic, 2005. Classification of medical images using energy information obtained from wavelet transform for medical image retrieval. Proceeding of 7th International Workshop on Enterprise Networking and Computing in Healthcare Industry, pp: 124-129.
    CrossRef    
12. Mohanapriya, S. and M. Vadivel, 2013. Automatic retrival of MRI brain image using multiqueries system. Proceeding of IEEE International Conference on Information Communication and Embedded Systems (ICICES, 2013), pp: 1099-1103.
    CrossRef    
13. Mojsilove, A. and J. Ciomes, 2002. Semantic based categorization, browsing and retrieval in medical image databases. Proceeding of International Conference on Image Processing, 3: 145-148.
    CrossRef    
14. Prasad, M., A. Sowmya and I. Koch, 2004. Efficient feature selection based on independent component analysis. Proceeding of the IEEE Intelligent Sensors, Sensor Networks and Information Processing Conference, pp: 427-432.
    
15. Shinde, A.D., 2004. A wavelet packet based sifting process and its application for structural health monitoring. M.A. Thesis, Faculty of Worcester Polytechnic Institute.
    
16. Valian, E., E. Mohanna and S. Tavakoli, 2011. Improved cuckoo search algorithm for global optimization. Int. J. Commun. Inform. Technol., 1(1): 31-44.
    
17. Varol, E., B. Gaonkar, G. Erus, R. Schultz and C. Davatzikos, 2012. Feature ranking based nested support vector machine ensemble for medical image classification. Proceeding of 9th IEEE International Symposium on Biomedical Imaging (ISBI, 2012), pp: 146-149.
    CrossRef    
18. Whitcher, B., V.J. Schmid and A. Thornton, 2011. Working with the DICOM and NIfTI data standards in R. J. Stat. Softw., 44(6): 1-28.
    CrossRef    
19. Yang, X.S. and S. Deb, 2009. Cuckoo search via Lévy flights. Proceeding of IEEE World Congress on Nature and Biologically Inspired Computing (NaBIC 2009), pp: 210-214.
    CrossRef    

Competing interests

The authors have no competing interests.

Open Access Policy

This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made.

Copyright

The authors have no competing interests.